no code implementations • 25 May 2024 • Ziao Yang, Han Yue, Jian Chen, Hongfu Liu
Various approaches, including matrix decomposition, have been explored to expedite and approximate the inversion of the Hessian matrix, with the aim of making influence functions applicable to deep models.
no code implementations • 10 Jul 2022 • Han Yue, Steve Xia, Hongfu Liu
META consists of Positional Encoding, Transformer-based Autoencoder, and Multi-task Prediction to learn effective representations for both migration prediction and rating prediction.
no code implementations • 19 May 2022 • Han Yue, Chunhui Zhang, Chuxu Zhang, Hongfu Liu
Recently, contrastiveness-based augmentation surges a new climax in the computer vision domain, where some operations, including rotation, crop, and flip, combined with dedicated algorithms, dramatically increase the model generalization and robustness.
no code implementations • 29 Sep 2021 • Han Yue, Jundong Li, Hongfu Liu
Unsupervised feature selection aims to select a subset from the original features that are most useful for the downstream tasks without external guidance information.
no code implementations • 1 Jan 2021 • Han Yue, Pengyu Hong, Hongfu Liu
In this paper, we propose a Graph-Graph Similarity Network to tackle the graph classification problem by constructing a SuperGraph through learning the relationships among graphs.